© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47669
    Prev
    Next
    INDEX
    Explanations

    the contraction it's

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on the apostrophe-s suffix (the “’s” seen in English contractions and possessives, e.g. “it’s,” “Darryl’s,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    It
    -3.08
    </td>
    -2.77
    This
    -2.73
    ܖ
    -2.53
    There
    -2.34
     These
    -2.33
    </sup>
    -2.23
    Since
    -2.17
    AutoresizingMask
    -2.13
    You
    -2.11
    POSITIVE LOGITS
     turmoil
    2.59
    籥
    2.53
     maquilla
    2.45
     continúas
    2.36
    廰
    2.30
    }
    2.22
    翃
    2.19
     può
    2.16
     enfati
    2.14
    轳
    2.14
    Activations Density 0.044%

    No Known Activations